Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 13
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

An edge computing wireless sensor network for diagnosing orange fruit disease

  • Foroughi, Arman
  • Lloret, Jaime|||0000-0002-0862-0533
  • Jimenez, Jose M.|||0000-0002-3688-7235
  • Sendra, Sandra|||0000-0001-9556-9088
[EN] This study introduces an innovative Edge Computing Wireless Sensor Network and Designing a new algorithm for diagnosing orange fruit diseases. The network combines Raspberry Pi using wireless technologies like Zigbee and LoRa with Wireless Mesh Routers using Wireless Technologies like LoRa and Cellular technologies. By using a new system that includes a YOLOv8 model and an image processing algorithm that detects the color spectrum of the diseased part of the fruit, it is possible to quickly identify certain diseases, such as canker, black spot, and melanosis. The system achieves a high accuracy of 92.2% in disease detection. This cost-effective and efficient solution offers farmers a practical tool for early disease detection, enabling timely interventions to protect crops and improve overall agricultural outcomes. In this study, in connection with the proposed algorithm, 97 images of diseased orange fruit, including Canker, melanosis, and black spot, as well as healthy oranges have been tested. It has also been tested in an orange orchard. The proposed new model successfully identified orange black spot disease with 30 correct detections out of 32 images and 2 errors, melanosis disease with 18 correct detections out of 21 images and 3 errors, canker disease with 9 correct detections out of 11 images and 2 errors, and 33 images of healthy oranges fruits with 100% accuracy. The Python codes for the proposed model and the dataset used in this study are available in a GitHub repository and accessible to the public., Ministerio de Ciencia e Innovacion, PID2020114467RRC33/AEI/https://doi.org/10.13039/501100011033,PID2020-114467RRC33/AEI/10.13039/501100011033,PID2020-114467RRC33/AEI/10.13039/501100011033,PID2020-114467RRC33/AEI/10.13039/501100011033, Ministerio de Economia y Competitividad, Spain, TED2021-131040BC31, TED2021-131040BC31, TED2021-131040BC31, TED2021-131040BC31
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A Comprehensive Survey of Drones for Turfgrass Monitoring

  • Parra, Lorena
  • Ivars-Palomares, Alberto
  • Ahmad, Ali|||0000-0001-5530-7374
  • Zaragoza-Esquerdo, Miguel
  • Sendra, Sandra|||0000-0001-9556-9088
  • Lloret, Jaime|||0000-0002-0862-0533
[EN] Drones are being used for agriculture monitoring in many different crops. Nevertheless, the use of drones for green areas' evaluation is limited, and information is scattered. In this survey, we focus on the collection and evaluation of existing experiences of using drones for turfgrass monitoring. Despite a large number of initial search results, after filtering the information, very few papers have been found that report the use of drones in green areas. Several aspects of drone use, the monitored areas, and the additional ground-based devices for information monitoring are compared and evaluated. The data obtained are first analysed in a general way and then divided into three groups of papers according to their application: irrigation, fertilisation, and others. The main results of this paper indicate that despite the diversity of drones on the market, most of the researchers are using the same drone. Two options for using cameras in order to obtain infrared information were identified. Moreover, differences in the way that drones are used for monitoring turfgrass depending on the aspect of the area being monitored have been identified. Finally, we have indicated the current gaps in order to provide a comprehensive view of the existing situation and elucidate future trends of drone use in turfgrass management., This work has been funded by the "Ministerio de Economia y Competitividad" through the Project TED2021-131040B-C31, and by the "Generalitat Valenciana" through the "Programa Investigo" project INVEST/2022/467.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Trust-based decentralized blockchain system with machine learning using Internet of agriculture things

  • Saba, Tanzila
  • Rehman, Amjad
  • Haseeb, Khalid
  • Bahaj, Saeed Ali
  • Lloret, Jaime|||0000-0002-0862-0533
[EN] The growth of Internet of Agriculture Things (IoAT) with wireless technologies has resulted in significant advances for smart farming systems. However, various techniques have been presented to predict the soil and crop conditions. Nonetheless providing a quality-enabled autonomous system is one of the important research challenges. Furthermore, in the event of network over-loading, most existing work needs help to handle trustworthy communication. As a result, this paper proposes a smart optimization model to develop reliable and quality-aware sustainable agriculture using machine learning. Firstly, the proposed model utilizes intelligent devices to automate the data collection and transmission. It analyzes the independent performance variables to support the consistent decision-making process for the forwarding scheme. Secondly, the proposed model investigated blockchain-based security principles for integrating the trusted system to reduce communication interference. The proposed model has been validated through simulations, and numerous experiments have demonstrated its efficacy regarding network parameters., This work has been funded by the "Ministerio de Ciencia e Innovacion "through the Project PID2020-114467RR-C33, by the "Ministerio de Economia y Competitividad" through the Project TED2021-131040B-C31, and by "Ministerio de Agricultura, Pesca y Alimentacion" through the "proyectos de innovacion de interes general por grupos operativos de la Asociacion Europea para la Innovacion en materia de productividad y sostenibilidad agrocolas (AEI -Agri) ", project GO TECNOGAR.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Employment of MQ gas sensors for the classification of Cistus ladanifer essential oils

  • Díaz-Blasco, Francisco Javier|||0009-0009-1458-7547
  • Viciano-Tudela, Sandra|||0000-0001-6621-0148
  • Ahmad, Ali|||0000-0001-5530-7374
  • Sendra, Sandra|||0000-0001-9556-9088
  • Lloret, Jaime|||0000-0002-0862-0533
  • Parra, Lorena
  • Chaloupková, Veronika
  • Bados, Raquel
  • Esteban Pascual, Luis Saul
  • Mediavilla, Irene
[EN] The chemical composition of essential oils (EOs) from Cistus ladanifer has a huge variability throughout the year, impacting the oil quality. Nowadays, EO analytic chemistry techniques, which are expensive and destroy the sample, are utilized to measure the chemical composition. In the paper, we propose a combination of low-cost sensors and machine learning based system. As low-cost sensors, seven gas sensors are combined to obtain up to 36 features. Regarding machine learning, 31 multiclass classification algorithms are applied. Data from sensors were collected for 33 samples of EO from Cistus ladanifer. The generated dataset was split into training and test datasets, with 75 % of the data for training. The datasets were created to ensure a homogeneous chemical composition distribution on both training and test datasets. There were three target chemical compounds: Alpha-pinene and Viridiflorol as individual compounds and Terpenic Hydrocarbons as a group of chemical compounds. The value of the percentage of each targeted compound is converted into a categoric variable with 5 possible values, 1 being the lowest concentration and 5 being the maximum one. The data of the MQ-sensors were included as the input for the models, and each one of the targeted chemical compounds was selected as an output for different models. The input features were ranged using different algorithms for the feature selection process. The results indicate that there is no valid classification model for Viridiflorol, and limited accuracy is achieved for Alpha-pinene. Meanwhile, for Terpenic Hydrocarbons, an accuracy of 91.6 % is achieved. It is important to highlight that these accuracies were attained when a reduced number of features were included, ranging the number of features from 11 to 13. This is the first case in which MQ-based gas sensors, or other metal oxide sensors, are used to correctly determine the concentration of a chemical compounds in a complex matrix formed by dozens of compounds. This system will provide a cheap method to determine the quality of EOs and confirm the benefits of combining low-cost sensors with machine learning., This work has been funded by the "Ministerio de Ciencia e Innovacion" through the Project PID2020-114467RR-C33/AEI/10.13039/501100011033, and by the "Ministerio de Economia y Competitividad" through the Project TED2021-131040B-C31. This study also forms part of the ThinkInAzul programme and was supported by MCIN with funding from European Union NextGenerationEU (PRTR-C17.I1) and by Generalitat Valenciana (THINKINAZUL/2021/002) . Llamada iniciada 13:02.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Low-Cost Optical Sensors for Soil Composition Monitoring

  • Díaz-Blasco, Francisco Javier|||0009-0009-1458-7547
  • Ahmad, Ali|||0000-0001-5530-7374
  • Sendra, Sandra|||0000-0001-9556-9088
  • Lloret, Jaime|||0000-0002-0862-0533
  • Parra, Lorena
[EN] Studying soil composition is vital for agricultural and edaphology disciplines. Presently, colorimetry serves as a prevalent method for the on-site visual examination of soil characteristics. However, this technique necessitates the laboratory-based analysis of extracted soil fragments by skilled personnel, leading to substantial time and resource consumption. Contrastingly, sensor techniques effectively gather environmental data, though they mostly lack in situ studies. Despite this, sensors offer substantial on-site data generation potential in a non-invasive manner and can be included in wireless sensor networks. Therefore, the aim of the paper is to develop a low-cost red, green, and blue (RGB)-based sensor system capable of detecting changes in the composition of the soil. The proposed sensor system was found to be effective when the sample materials, including salt, sand, and nitro phosphate, were determined under eight different RGB lights. Statistical analyses showed that each material could be classified with significant differences based on specific light variations. The results from a discriminant analysis documented the 100% prediction accuracy of the system. In order to use the minimum number of colors, all the possible color combinations were evaluated. Consequently, a combination of six colors for salt and nitro phosphate successfully classified the materials, whereas all the eight colors were found to be effective for classifying sand samples. The proposed low-cost RGB sensor system provides an economically viable and easily accessible solution for soil classification., This work is partially funded by the "Programa Estatal de I + D + i Orientada a los Retosde la Sociedad, en el marco del Plan Estatal de Investigacion Cientifica y Tecnica y de Innovacion 2017-2020" project PID2020-114467RR-C33/AEI/10.13039/501100011033 and by "Proyectos Estrate-gicos Orientados a la Transicion Ecologica y a la Transicion Digital" project TED2021-131040B-C31. This study also forms part of the ThinkInAzul program and was supported by MCIN with funding from the European Union NextGenerationEU (PRTR-C17.I1) and from Generalitat Valenciana(THINKINAZUL/2021/002).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Machine Learning Unlocks Chemometric Profiling of Plant-Derived Metabolites Using Spectral and Gas Sensor Fingerprints

  • Ahmad, Ali|||0000-0001-5530-7374
  • Díaz, Francisco Javier
  • Sendra, Sandra|||0000-0001-9556-9088
  • Lloret, Jaime|||0000-0002-0862-0533
[EN] Essential oils (EOs) are chemically complex natural matrices whose quality and bioactivity are governed by structurally diverse secondary metabolites. Conventional techniques such as gas chromatography-mass spectrometry (GC-MS) provide detailed compositional profiling, yet they remain costly, labor-intensive, and unsuitable for real-time monitoring. Here, we present a multimodal chemometric framework that integrates UV-Vis-NIR spectroscopy (190-1100 nm) with low-cost metal oxide gas sensors to quantitatively predict EO metabolite concentrations using machine learning. Multivariate analyses employing t-distributed stochastic neighbor embedding (t-SNE), uniform manifold approximation and projection (UMAP), and correlation mapping revealed chemically coherent clustering of Cistus ladanifer EO samples and biochemical associations between sensor responses and metabolite families, highlighting the richness of the fused feature space. Metabolites identified by GC-MS were grouped into seven functional classes including terpenic hydrocarbons, sesquiterpenic hydrocarbons, alcohols, aldehydes, ketones, esters, and residuals. These groupings guided targeted regression modeling. Data validation was performed against GC-MS quantified metabolites. Among the tested algorithms, Ridge regression achieved the highest predictive performance (R2 = 0.999). Lasso regression followed with R2 = 0.971, favoring sparsity at the expense of completeness. Partial least squares algorithm failed to capture variance in the high-dimensional multimodal dataset. Feature attribution based on Shapley values demonstrated that accurate predictions required the joint contribution of distributed spectral bands and complementary sensor responses, underscoring the necessity of multimodal fusion for resolving chemically heterogeneous and low-abundance metabolites. This work establishes a scalable, non-destructive, and real-time strategy for EO profiling, with broad implications for traceability, sustainable cultivation, and smart agriculture, and illustrates the transformative role of machine learning in chemometric exploration of natural products., This work has been funded by the "Ministerio de Ciencia e Innovacion" through the Project PID2020-114467RR-C33/AEI/10.13039/501100011033, and by the "Ministerio de Economia y Competitividad" through the Project TED2021-131040B-C31; and by the Grant PRE2021-1008 09 funded by Agencia Estatal de Investigacion (AEI) MICIU/AEI/10.13039/501100011033 and by the European Social Fund Plus (ESF+).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Diagnosis of orange tree fruit and leaf diseases based on a new deep learning model using a graphical user interface

  • Foroughi, Arman
  • Jimenez, Jose M.|||0000-0002-3688-7235
  • Lloret, Jaime|||0000-0002-0862-0533
[EN] Identifying the spectrum of fruit and leaf disease is one of the important pillars for farmers to correctly diagnose orange disease and quickly treat it so that it does not spread to other orange trees. For this purpose, we designed an Android and iOS application that can detect orange fruit and leaf diseases, such as melanosis, black spots, canker, and greening, as well as detect healthy oranges. It also declares everything but oranges as Not Orange¿. In this case, farmers no longer need specialists to diagnose fruit disease. A new deep learning model has been proposed and built to diagnose the type of orange fruit disease. KIVY framework and KV language were used for graphical programming in Android, iOS, Windows, Linux, and Raspberry Pi operating systems. To learn the proposed model, an image dataset of orange disease and orange tree leaves, containing 5073 images, was used. We have provided data images to the proposed deep learning model algorithm so that the new model can be trained by processing these images. Powerful hardware is required for image processing operations in deep learning networks. For this purpose, we used Google Collaboratory. The output of this newly trained model can be used in Windows and Linux. However, they cannot be used in mobile hardware or Android OS. Therefore, we converted the proposed new trained model to TensorFlow lite, which can be implemented in mobile phones and Android and iOS operating systems and has been optimized for this purpose. We then created an Android package using the python-for-Android project. The Buildozer tool was used to automate the entire process. The trained model could detect canker, melanosis, greening, and black spots with 98.29% accuracy. This application is easily available to farmers, who can easily detect diseases in oranges and orange tree leaves., This work has been funded by the Ministerio de Ciencia e Innovacion¿ through the Project PID2020-114467RRC33 /AEI/10.13039/501100011033 and by the Ministerio de Economía y Competitividad through the Project TED2021-131040BC31.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Tesis doctoral (DoctoralThesis)

A Sensor System to Remote Monitor Patients with Chronic Diseases and their Environment in Coastal Areas

  • Viciano-Tudela, Sandra|||0000-0001-6621-0148
[ES] En los últimos años, el auge de la tecnología se ha disparado de manera considerable llegando a incluirse el ámbito de la salud. Distintas aplicaciones y dispositivos han sido creados para la detección y ayuda en el diagnostico de pacientes con enfermedades crónicas. Sin embargo, esta monitorización, en la mayoría de ocasiones, no tiene en cuanta ni el en-torno donde habita o realiza actividades la persona ni los hábitos del día a día de esta. Por otro lado, tampoco tiene en cuenta como le afectan de manera individual los contaminantes que los rodean. Incluyendo contaminantes del agua que les rodea, del agua que beben, o incluso del agua con la que se riegan los jardines donde disfrutan de su ocio. Tampoco tienen en cuenta como es el ambiente que les rodea y si es beneficioso o perjudicial según la enfermedad que padecen. Por otro lado, aunque existen a nivel hospitalario multitud de sistemas de monitorización, estos no son accesibles a nivel de usuario y en muchas ocasiones tener este tipo de dispositivos en el hogar del paciente, permitiría, por un lado, reducir la presión de número de pacientes a nivel hospitalario, así como obtener mayor rapidez en el diagnóstico de cara al propio paciente. Siempre teniendo en cuenta, que estos dispositivos, en ningún caso pueden ni deben sustituir el diagnóstico y tratamientos llevado a cabo por el facultativo, ni las pruebas realizadas por este, pero si pueden acelerar los resultados preliminares. Además, los dispositivos que se suelen utilizar no tienen en cuenta las necesidades ya no solo de salud, si no digitales que puede presentar este tipo de personas, incluyendo personas de avanzada edad. En este contexto, surge la necesidad de desarrollar sensores de bajo coste y de fácil manipulación, que además de permitir la monitorización individual de la propia persona, tenga en cuenta su entorno y su forma de vida. Además, de que estos dispositivos puedan estar al alcance de todos sin brechas económicas las cuales, en muchas ocasiones limitan el alcance a la población. De esta forma se puede conseguir mejorar la calidad de vida de personas con enfermedades crónicas. Por todo ello, en esta tesis, se han identificado diferentes parámetros de calidad de agua, como el pH, la turbidez, la salinidad, entre otros. Se han detectado diferentes concentraciones de medicamentos en agua, la cual puede llegar a las fuentes de agua potable y ser perjudicial para la salud. Así como concentraciones de salinidad en el agua que rodea a estos pacientes. Por otro lado, se ha detectado diferentes áreas de la zona marítimo costera, las cuales, según sus características pueden ser zonas óptimas para realizar actividades de ocio, o si por el contrario la zona no es apta para la persona con enfermedad crónica. Se ha utiliza-do un pulsioxímetro para obtener parámetros que actualmente los pulsioxímetros comercia-les de bajo coste no los incluyen, además de implementar una aplicación para que el usuario pueda almacenar sus datos y en tal caso enseñárselos al médico. También, se ha detectado la fatiga permitiendo establecer que personas la padecen y cuáles no. Se ha detectado sangre en orina de manera no invasiva y finalmente se ha desarrollado una botella inteligente para incentivar el consumo de líquidos para evitar la deshidratación. Para llevar a cabo estas implementaciones, en esta tesis, se ha desarrollado un sistema de sensores para la monitorización remota de pacientes con enfermedades crónicas y su en-torno en zonas del litoral marítimo. Para ello, en primer lugar, se ha visto las limitaciones de cada uno de los sensores que existen actualmente y que están relacionados con los parámetros que queremos medir. Seguidamente, se ha dividido el escenario principal en tres subescenarios, según la naturaleza y disposición del sensor. A continuación, se han desarrollado los diferentes sensores para poder medir y obtener datos de los parámetros citados anteriormente y se han analizado los resultados., [EN] In recent years, technological advances have skyrocketed, even extending into the healthcare sector. Various applications and devices have been developed to detect and sup-port the diagnosis of patients with chronic diseases. However, this monitoring, in most cases, fails to consider the environment where the person lives or carries out their activities, nor their daily habits. Furthermore, it does not take into account how pollutants in their surroundings affect them individually. This includes pollutants in the water they inhabit, the water they drink, or even the water used to irrigate the gardens where they enjoy leisure activities. Nor does it consider the nature of their environment and whether it is beneficial or detrimen-tal to the specific disease they suffer from. On the other hand, although numerous hospital monitoring systems exist, they are not accessible to the general public. Having these devices in patients' homes would, in many cases, reduce pressure on hospitals and allow for faster diagnosis. It's important to remember that these devices cannot and should not replace the diagnosis and treatment provided by a physician, nor the tests they perform, but they can accelerate preliminary results. Furthermore, the devices currently in use do not take into account the digital needs of individuals, in-cluding older people, who may need support not only for their health but also for their ove-rall well-being. In this context, there is a need to develop low-cost, easy-to-use sensors that, in addition to enabling individual monitoring, also consider a person's environment and lifestyle. Moreover, these devices should be accessible to everyone, eliminating the economic barriers that often prevent many from accessing them. This approach can improve the quality of life for people with chronic illnesses. Therefore, this thesis identifies various water quality parameters, including pH, turbidity, and salinity. Different concentrations of medications have been detected in water, which can reach drinking water sources and pose a health risk. Salinity concentrations have also been measured in the water surrounding these patients. Furthermore, different areas of the coastal zone have been identified that, depending on their characteristics, may be optimal for leisure activities or, conversely, unsuitable for individuals with chronic illnesses. A pulse oximeter has been used to obtain parameters not currently included in low-cost commercial pulse oximeters. An application has also been implemented so that users can store their data and, if necessary, share it with their doctors. Fatigue has also been detected, allowing resear-chers to determine which individuals experience it and which do not. Blood in urine has been detected non-invasively, and finally, a smart bottle has been developed to encourage fluid intake and prevent dehydration. To implement these solutions, this thesis presents the development of a sensor system for the remote monitoring of patients with chronic diseases and their environment in coastal areas. First, the limitations of existing sensors related to the parameters to be measured were examined. Next, the main scenario was divided into three sub-scenarios based on the sensor's nature and configuration. Subsequently, the various sensors were developed to measure and collect data on the aforementioned parameters, and the results were analyzed. Finally, the thesis demonstrates how some of the developed sensors could be implemented in other areas., [CA] En els últims anys, l'auge de la tecnologia s'ha incrementat de manera considerable, arribant també a l'àmbit de la salut. Diferents aplicacions i dispositius han sigut creats per a la detecció i l'ajuda en el diagnòstic de pacients amb malalties cròniques. No obstant això, aquesta monitorització, en la majoria dels casos, no té en compte ni l'entorn on viu o realitza activitats la persona ni els seus hàbits quotidians. D'altra banda, tampoc considera com els afecten de manera individual els contaminants que els envolten, incloent-hi contaminants de l'aigua del seu entorn, de l'aigua que beuen o fins i tot de l'aigua amb què es reguen els jardins on gaudeixen del seu temps d'oci. Tampoc es té en compte com és l'ambient que els envolta ni si resulta beneficiós o perjudicial segons la malaltia que pateixen. D'altra banda, encara que a nivell hospitalari existeixen nombrosos sistemes de monitorització, aquests no són accessibles a nivell d'usuari i, en moltes ocasions, disposar d'aquest tipus de dispositius a la llar del pacient permetria, d'una banda, reduir la pressió del nombre de pacients en l'àmbit hospitalari i, d'altra banda, obtindre una major rapidesa en el diagnòstic per al mateix pacient. Sempre tenint en compte que aquests dispositius, en cap cas, poden ni han de substituir el diagnòstic i els tractaments realitzats pel facultatiu, ni les proves efectuades per aquest, però sí que poden accelerar l'obtenció de resultats preliminars. A més, els dispositius que habitualment s'utilitzen no tenen en compte no sols les necessitats de salut, sinó també les necessitats digitals que poden presentar aquest tipus de persones, incloent-hi les persones d'edat avançada. En aquest context, sorgeix la necessitat de desenvolupar sensors de baix cost i de fàcil manipulació que, a més de permetre la monitorització individual de la pròpia persona, tin-guen en compte el seu entorn i la seua manera de vida. A més, és important que aquests dis-positius estiguen a l'abast de tothom sense bretxes econòmiques que, en moltes ocasions, limiten el seu accés a una part de la població. D'aquesta manera es pot contribuir a millorar la qualitat de vida de les persones amb malalties cròniques. Per tot això, en aquesta tesi s'han identificat diferents paràmetres de qualitat de l'aigua, com el pH, la terbolesa, la salinitat, entre altres. S'han detectat diferents concentra-cions de medicaments en l'aigua, que poden arribar a les fonts d'aigua potable i resultar per-judicials per a la salut. Així mateix, s'han analitzat concentracions de salinitat en l'aigua que envolta aquests pacients. D'altra banda, s'han identificat diferents àrees de la zona marítim-costanera que, segons les seues característiques, poden ser zones òptimes per a realitzar acti-vitats d'oci o, per contra, no resultar adequades per a persones amb malalties cròniques. També s'ha utilitzat un pulsioxímetre per a obtindre paràmetres que actualment els pulsioxímetres comercials de baix cost no inclouen, a més d'implementar una aplicació per-què l'usuari puga emmagatzemar les seues dades i, si cal, mostrar-les al metge. Igualment, s'ha detectat la fatiga, cosa que ha permés determinar quines persones la pateixen i quines no. S'ha detectat sang en l'orina de manera no invasiva i, finalment, s'ha desenvolupat una botella intel·ligent per a incentivar el consum de líquids i evitar la deshidratació. Per a dur a terme aquestes implementacions, en aquesta tesi s'ha desenvolupat un sistema de sensors per a la monitorització remota de pacients amb malalties cròniques i del seu entorn en zones del litoral marítim. Per a això, en primer lloc, s'han analitzat les limitacions de cadascun dels sensors existents actualment relacionats amb els paràmetres que es volen mesurar. Seguidament, s'ha dividit l'escenari principal en tres subescenaris segons la natura-esa i la disposició del sensor. A continuació, s'han desenvolupat els diferents sensors per a mesurar i obtindre dades dels paràmetres esmentats., To complete this thesis I have participated in the following projects: • FISABIO C.V. Contrato de beca en prácticas en investigación biomédica (UPV-FISABIO-2020-A43). • Edge Computing Inteligente en Redes Inalambricas Heterogeneas de Sensores para la Agricultura de Precision y la Diseminacion de la Agricultura Digital (Solucion) (TED2021-131040B-C31). • Red heterogénea inteligente de sensores inalámbricos para monitorizar y estimar el contenido de resina de Cistus ladanifer. (BIOCISTUS) PID2020-114467RRC33/AEI/10.13039/501100011033 27 • ThinkInAzul programme and was supported by MCIN with funding from European Union NextGenerationEU (PRTR-C17.I1) and by Generalitat Valenciana (THINKINAZUL/2021/002).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Multivariate Gas Sensor E-Nose System with PARAFAC and Machine Learning Modeling for Quantifying and Classifying the Impact of Fishing Gears

  • Silva-Alvarado, Vinie Lee|||0009-0000-5857-3248
  • Lloret, Jaime|||0000-0002-0862-0533
[EN] The quality of seafood is intrinsically linked to the accumulated history of stress, feeding, handling, and physical damage imposed by the fishing gear employed. This study proposes an innovative methodology using an E-nose sensor. The study species was Sparus aurata. Eight fishing gears were studied. The methodology integrates Parallel Factor Analysis (PARAFAC) for impact quantification and Machine Learning (ML) for classifying the fishing gear of origin. Longline was established as the method with the lowest deviation. The impact hierarchy, from highest to lowest deviation, is as follows: Aquaculture 50.61% (95% CI: 34%, 68%), Purse seine 37.92% (95% CI: 22%, 54%), Trawl 35.92% (95% CI: 21%, 51%), Gillnet (three panels) 27.69% (95% CI: 14%, 41%), Gillnet (single panel) 24.63% (95% CI: 9%, 40%), Gillnet (two panels) 18.12% (95% CI: 4%, 31%) and Hook and line 1.36% (95% CI: ¿10%, 13%). For the classification task, 33 ML models were evaluated. Subspace KNN model yielded the best results with an accuracy of 97.14% in the validation and 98.08% in the testing, using 35 variables. Using 10, 15, 20, 25, and 30 variables, an accuracy higher than 85% was achieved. These results demonstrate the high precision in fish traceability by exploiting the sensor response profile left by each fishing gear., This work has been funded by the Ministerio de Economía y Competitividad through the Project TED2021-131040B-C31. This study also forms part of the ThinkInAzul programme and was supported by MCIN with funding from European Union NextGenerationEU (PRTR-C17.I1) and by Generalitat Valenciana (THINKINAZUL/2021/002). The author V.L.S.-A. is supported by a contract from the Universitat Politècnica de València through the Programa de Ayudas de Investigación y Desarrollo (PAID-01-24) .
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Proposal of a New System for Essential Oil Classification Based on Low-Cost Gas Sensor and Machine Learning Techniques

  • Viciano-Tudela, Sandra|||0000-0001-6621-0148
  • Sendra, Sandra|||0000-0001-9556-9088
  • Lloret, Jaime|||0000-0002-0862-0533
  • Parra, Lorena
  • Navarro-García, Paula
[EN] Essential oils are valuable in various industries, but their easy adulteration can cause adverse health effects. Electronic nasal sensors offer a solution for adulteration detection. This article proposes a new system for characterising essential oils based on low-cost sensor networks and machine learning techniques. The sensors used belong to the MQ family (MQ-2, MQ-3, MQ-4, MQ-5, MQ-6, MQ-7, and MQ-8). Six essential oils were used, including Cistus ladanifer, Pinus pinaster, and Cistus ladanifer oil adulterated with Pinus pinaster, Melaleuca alternifolia, tea tree, and red fruits. A total of up to 7100 measurements were included, with more than 118 h of measurements of 33 different parameters. These data were used to train and compare five machine learning algorithms: discriminant analysis, support vector machine, k-nearest neighbours, neural network, and naive Bayesian when the data were used individually or when hourly mean values were included. To evaluate the performance of the included machine learning algorithms, accuracy, precision, recall, and F1-score were considered. The study found that using k-nearest neighbours, accuracy, recall, F1-score, and precision values were 1, 0.99, 0.99, and 1, respectively. The accuracy reached 100% with k-nearest neighbours using only 2 parameters for averaged data or 15 parameters for individual data., This work is partially funded by the Programa Estatal de I + D + i Orientada a los Retos de la Sociedad, en el marco del Plan Estatal de Investigacion Cientifica y Tecnica y de Innovacion 2017-2020 project PID2020-114467RR-C33/AEI/10.13039/501100011033 and by "Proyectos Estrategicos Orientados a la Transicion Ecologica y a la Transicion Digital" project TED2021-131040B-C31.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Low-Cost Microcontroller-Based Multiparametric Probe for Coastal Area Monitoring

  • Parra, Lorena
  • Carrasco, David
  • Viciano-Tudela, Sandra|||0000-0001-6621-0148
  • Sendra, Sandra|||0000-0001-9556-9088
  • Lloret, Jaime|||0000-0002-0862-0533
[EN] The monitoring of the coastal environment is a crucial factor in ensuring its proper management. Nevertheless, existing monitoring technologies are limited due to their cost, temporal resolution, and maintenance needs. Therefore, limited data are available for coastal environments. In this paper, we present a low-cost multiparametric probe that can be deployed in coastal areas and integrated into a wireless sensor network to send data to a database. The multiparametric probe is composed of physical sensors capable of measuring water temperature, salinity, and total suspended solids (TSS). The node can store the data in an SD card or send them. A real-time clock is used to tag the data and to ensure data gathering every hour, putting the node in deep sleep mode in the meantime. The physical sensors for salinity and TSS are created for this probe and calibrated. The calibration results indicate that no effect of temperature is found for both sensors and no interference of salinity in the measuring of TSS or vice versa. The obtained calibration model for salinity is characterised by a correlation coefficient of 0.9 and a Mean Absolute Error (MAE) of 0.74 g/L. Meanwhile, different calibration models for TSS were obtained based on using different light wavelengths. The best case was using a simple regression model with blue light. The model is characterised by a correlation coefficient of 0.99 and an MAE of 12 mg/L. When both infrared and blue light are used to prevent the effect of different particle sizes, the determination coefficient of 0.98 and an MAE of 57 mg/L characterised the multiple regression model., This work has been funded by the "Ministerio de Ciencia e Innovacion" through the Project PID2020-114467RR-C33/AEI/10.13039/501100011033, by "Ministerio de Agricultura, Pesca y Alimentacion" through the "proyectos de innovacion de interes general por grupos operativos de la Asociacion Europea para la Innovacion en materia de productividad y sostenibilidad agricolas (AEI-Agri)", project GO TECNOGAR, and by the "Ministerio de Economia y Competitividad" through the Project TED2021-131040B-C31. This study also forms part of the ThinkInAzul programme and was supported by MCIN with funding from European Union NextGenerationEU (PRTR-C17.I1) and by Generalitat Valenciana (THINKINAZUL/2021/002).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

LEA-RPL: lightweight energy-aware RPL protocol for internet of things based on particle swarm optimization

  • Mokrani, Sabrina
  • Belkadi, Malika
  • Sadoun, Tassadit
  • Aoudjit, Rachida
  • Lloret, Jaime|||0000-0002-0862-0533
[EN] This paper addresses the issue of quality of service routing optimization within the Internet of Things networks. We particularly focus on the energy-aware and the lightweight aspects. By recognizing the relationship between lightweight and energy-aware routing, we set out to study their combined benefits. This study aims to enhance the Routing Protocol for Low Power and Lossy Networks by integrating energy-awareness and lightweight characteristics based on the Particle Swarm Optimization algorithm. Our approach addresses energy consumption, routing overhead and decision complexity in route establishment. The principal contributions include the introduction of an objective function that considers Expected Life Time, Delay and a new proposed metric Energy Aware-Expected Transmission Count. The improvement of the Long Short Term Memory predicting inertia weight based PSO with Online Gradient Descent that is used to optimize both the parent selection process and Trickle Timer mechanism. The controlled parent switching process to solve unnecessary and frequent changes. Our approach is validated through simulations in Contiki COOJA, with thorough comparisons with some existing protocols based on packet delivery ratio, average energy consumption, convergence time, control overhead, average end-to-end delay and average parent switching as performance metrics. The results reveal that our approach performs better. Depending on the protocol used for comparison, our approach reduced parent switching by 42.59-61.73%, convergence time by 20.31-66.06%, control overhead by 14.4-23.64%, energy consumption by 29.86-49.6%, end-to-end delay by 7.66-40.81% and increased packet delivery ratio by 2-42.92%., This work has been funded by the "Ministerio de Economia y Competitividad" through the Project TED2021-131040B-C31.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Proposal of a Gas Sensor-Based Device for Detecting Adulteration in Essential Oil of Cistus ladanifer

  • Viciano-Tudela, Sandra|||0000-0001-6621-0148
  • Sendra, Sandra|||0000-0001-9556-9088
  • Jimenez, Jose M.|||0000-0002-3688-7235
  • Lloret, Jaime|||0000-0002-0862-0533
  • Parra, Lorena
[EN] Essential oils are a valuable raw material for several industries. Low-cost methods cannot detect its adulteration; specialised equipment is required. In this paper, we proposed the use of gas sensors to detect the adulteration process in the essential oil of Cistus ladanifer. Gas sensors are used in a measuring chamber to measure pure and adulterated oils. We compare the suitability of the tested sensors for detecting adulterated oil and the required measuring time. A total of five samples are determined, with a measuring time of 12 h. Each gas sensor is configured to be sensitive to different compounds. Even though sensors are not specific to detect the volatile organic compounds (VOCs) present in the essential oil, our objective is to evaluate if these VOCs might interact with the sensors as an interferent. Results indicate that various gas sensors sensitive to the same chemical compound offered different values. It might indicate that the interaction of VOCs is different among the tested sensors or that the location of the sensors and the heterogeneous distribution of VOCs along the measurement chamber impact the data. Regarding the performed analyses, we can affirm that identifying the adulterated essential oil is possible using the generated data. Moreover, the results suggest that most of the data, even for different compounds and sensors, are highly correlated, allowing a reduction in the studied variables. According to the high correlation, data are reduced, and 100% of correct classification can be obtained even when only the MQ3 and MQ8 are used., This work has been funded by the "Ministerio de Ciencia e Innovacion" through the Project PID2020-114467RR-C33/AEI/10.13039/501100011033, by "Ministerio de Agricultura, Pesca y Alimentacion" through the "proyectos de innovacion de interes general por grupos operativos de la Asociacion Europea para la Innovacion en materia de productividad y sostenibilidad agricolas (AEI-Agri)", project GO TECNOGAR, and by the "Ministerio de Economia y Competitividad" through the Project TED2021-131040B-C31.